Repository navigation
fix(prompts,loading): require snapshot checklist row and preserve evidence grounding - #2033
Merged
chris-beckman merged 2 commits intoNov 9, 2026
Merged
Conversation
…dence grounding Signed-off-by: Chris Beckman <chris@paintedwolf.ai>
chris-beckman
marked this pull request as ready for review
November 8, 2026 23:18
github-merge-queue
Bot
removed this pull request from the merge queue due to failed status checks
Nov 9, 2026
Contributor
|
Removed from the merge queue: |
TestForegroundCancelsTitleAcrossAliases renders the title summarizer inside a synctest bubble. When the guidance catalog is cold, that render resolves the extension catalog and contends on the cross-process extension lock, whose five-second real-clock retry deadline collapses on the bubble's fake clock; the render fails, the summarizer returns before starting the provider, and the bubble deadlocks. Reproduced deterministically on pristine main by holding the lock file, so this is a pre-existing load-sensitive flake, not a regression. Give the subtest a private config root so catalog resolution never contends on the shared lock, and select on the summarizer result so an early return fails with the real error instead of deadlocking. Signed-off-by: Chris Beckman <chris@paintedwolf.ai>
github-merge-queue
Bot
removed this pull request from the merge queue due to failed status checks
Nov 9, 2026
Contributor
|
Removed from the merge queue: |
github-merge-queue
Bot
removed this pull request from the merge queue due to failed status checks
Nov 9, 2026
Contributor
|
Removed from the merge queue: |
github-merge-queue
Bot
removed this pull request from the merge queue due to failed status checks
Nov 9, 2026
Contributor
|
Removed from the merge queue: |
github-merge-queue
Bot
removed this pull request from the merge queue due to failed status checks
Nov 9, 2026
Contributor
|
Removed from the merge queue: |
2 tasks done
chris-beckman
deleted the
feat/progress-snapshot-and-evidence-grounding
branch
November 9, 2026 13:05
2 tasks done
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
update_progress.yamlcontent.descriptionso initial checklist creation includes a separate final snapshot row for user-facing CLI, terminal, or web UI work.claim-evidencefromturn.guides.omittableindecisions.yamland includecommandinclaim-evidence.mdneeded_withso runtime/screen evidence requirements remain present during build turns.toolEventOfferedToolsso stock skills referencing companion session tools stay eligible duringObserveToolCall.Merge-queue flake fix
The merge-group run failed on
TestForegroundCancelsTitleAcrossAliases/stream=true, a pre-existing load-sensitive flake on main: a cold guidance-catalog render inside the synctest bubble contends on the cross-process extension lock, whose real-clock retry deadline collapses on the bubble's fake clock, so the summarizer returns before starting the provider and the bubble deadlocks.Ported the test-side stabilization from #2036 (commit
8b480744fb) onto this branch: the subtest now uses a private config root (LYCAON_CONFIG_DIRtemp dir) so catalog resolution never contends on the shared lock, and selects on the summarizer result so an early return fails with the real error instead of deadlocking. No product changes; the #2036 contract fix was not ported.0a86450785e144df5d1422ec370eb6518e027837(cherry-pick of8b480744fb, DCO signed, pushed as a normal fast-forward)../task test:digest -- ./internal/llm/... ./internal/session/loading/...— 22 packages, 2339 passed / 0 failed / 0 skipped (receipt98a5ad65180e49ceb878b072cba2c484/00000000000000000001-439c95ef7c55429ca4348ca726bf2507.json)../task lint:full --scope ./internal/llmand--scope ./internal/session/loading— scope stages clean (0 issues.); the overall run exits only on the known pre-existing darwin whole-program deadcode artifact (41 findings in unrelated linux-tagged packages).bash scripts/ci_policy/static-checks.sh— exit 0 with the pinned gofmt (the default go1.27.3 run flags only the two known pre-existing files).